Triple
T21909079
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kathmandu District |
E541014
|
entity |
| Predicate | hasMajorEthnicGroup |
P1898
|
FINISHED |
| Object | Newar |
—
|
NE NERFINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Newar | Statement: [Kathmandu District, hasMajorEthnicGroup, Newar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Newar Context triple: [Kathmandu District, hasMajorEthnicGroup, Newar]
-
A.
Newar
chosen
Newar are an indigenous ethnic group of the Kathmandu Valley in Nepal, known for their rich urban culture, craftsmanship, and Newar language.
-
B.
Newar language
The Newar language is an indigenous Sino-Tibetan language of Nepal, historically associated with the Newar people and the Kathmandu Valley’s rich literary and cultural traditions.
-
C.
Tharu
The Tharu are an indigenous ethnic group from the Terai region of Nepal and northern India, known for their distinct language, culture, and traditional agrarian lifestyle.
-
D.
Thakuri
Thakuri is a high-status Khas caste group of Nepal traditionally associated with nobility and ruling elites.
-
E.
Newa
Newa is a Unicode block that encodes the Newa script used for writing the Nepal Bhasa (Newar) language of the Newar people in Nepal.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69e0c47b4e8c81908c8076eaa4c8e4f2 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f121d8c3108190a178ec6b3857da3f |
completed | April 28, 2026, 9:08 p.m. |
Created at: April 16, 2026, 7:39 p.m.